© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9701
    Prev
    Next
    INDEX
    Explanations

    Firefox browser behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    -3.50
     â
    -2.94
    u
    -2.64
    /
    -2.55
    हम
    -2.47
    ?
    -2.42
    )
    -2.38
    ter
    -2.38
     cheery
    -2.36
     jovial
    -2.31
    POSITIVE LOGITS
     erhi
    2.91
    鰾
    2.64
    　＊
    2.64
     Они
    2.45
    และ
    2.44
            
    2.36
    緇
    2.36
     ulei
    2.34
    Ꮚ
    2.31
    たまに
    2.28
    Activations Density 0.010%

    No Known Activations